Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting in legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal and technical language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.59
     AssemblyCulture
    -0.51
    fillType
    -0.47
    gameserver
    -0.45
    DIPSETTING
    -0.44
     endwhile
    -0.41
    mpo
    -0.40
     للمعارف
    -0.40
     fia
    -0.39
    EndContext
    -0.38
    POSITIVE LOGITS
    ⟬
    0.47
     noastre
    0.47
     față
    0.45
     brancas
    0.45
     umane
    0.44
     meisjes
    0.44
    íssima
    0.43
    gehenden
    0.43
     umana
    0.43
     acestui
    0.42
    Act Density 0.003%

    No Known Activations